Personalized Federated Learning with Server-Side Information
This work addresses computational efficiency and performance in personalized federated learning for applications with server-side data, representing an incremental improvement over prior methods.
The paper tackles the challenge of heavy client-side computation in personalized federated learning by proposing FedSIM, a method that uses server-side data to improve meta-gradient calculations, resulting in up to 34.2% faster convergence and superior accuracy compared to existing methods.
Personalized Federated Learning (FL) is an emerging research field in FL that learns an easily adaptable global model in the presence of data heterogeneity among clients. However, one of the main challenges for personalized FL is the heavy reliance on clients' computing resources to calculate higher-order gradients since client data is segregated from the server to ensure privacy. To resolve this, we focus on a problem setting where the server may possess its own data independent of clients' data -- a prevalent problem setting in various applications, yet relatively unexplored in existing literature. Specifically, we propose FedSIM, a new method for personalized FL that actively utilizes such server data to improve meta-gradient calculation in the server for increased personalization performance. Experimentally, we demonstrate through various benchmarks and ablations that FedSIM is superior to existing methods in terms of accuracy, more computationally efficient by calculating the full meta-gradients in the server, and converges up to 34.2% faster.